Where to troubleshoot Intel PRO/1000 performance problems?

[Mark Kirkwood]

Sally Janghos wrote:
> Aaron,
> 
>   Thanks for your reply.  Here is some output from some dd's on the disk that I'm reading/writing to.  
> 
>> dd if=/dev/zero of=testfile count=1000000;dd if=testfile of=/dev/null
> 1000000+0 records in
> 1000000+0 records out
> 512000000 bytes transferred in 27.951769 secs (18317267 bytes/sec)
> 1000000+0 records in
> 1000000+0 records out
> 512000000 bytes transferred in 16.864945 secs (30358830 bytes/sec)
>> dd if=/dev/zero of=testfile count=1000000 ; dd if=testfile of=/dev/null
> 1000000+0 records in
> 1000000+0 records out
> 512000000 bytes transferred in 28.492921 secs (17969376 bytes/sec)
> 1000000+0 records in
> 1000000+0 records out
> 512000000 bytes transferred in 16.605797 secs (30832607 bytes/sec)
> 
>   Am I reading right, the max network transfer rate from this disk will be between 143Mbit and 246Mbit/sec?  Is there a way to determine if there is an IRQ conflict?  How do you find out what IRQ's are currently used by the system?

To see bigger transfer rates you might want to retest with a bigger 
block size for the dd - e.g (FreeBSD 6.2 on a PIII 1.26Ghz with Promise 
ATA controller 2xSeagate IDE RAID0):

$ dd if=/dev/zero of=testfile bs=8k count=64000 ; dd if=testfile bs=8k 
of=/dev/null
64000+0 records in
64000+0 records out
524288000 bytes transferred in 11.624216 secs (45103084 bytes/sec)
64000+0 records in
64000+0 records out
524288000 bytes transferred in 1.544103 secs (339542136 bytes/sec)

Note for the read is clearly coming from memory (2 IDE disks will do 100 
MBytes/s max - not 300!).

Cheers

Mark